all AI news
Identifying Linear Relational Concepts in Large Language Models
April 2, 2024, 7:52 p.m. | David Chanin, Anthony Hunter, Oana-Maria Camburu
cs.CL updates on arXiv.org arxiv.org
Abstract: Transformer language models (LMs) have been shown to represent concepts as directions in the latent space of hidden activations. However, for any human-interpretable concept, how can we find its direction in the latent space? We present a technique called linear relational concepts (LRC) for finding concept directions corresponding to human-interpretable concepts by first modeling the relation between subject and object as a linear relational embedding (LRE). We find that inverting the LRE and using earlier …
abstract arxiv concept concepts cs.ai cs.cl hidden however human language language models large language large language models linear lms relational space transformer transformer language models type
More from arxiv.org / cs.CL updates on arXiv.org
Jobs in AI, ML, Big Data
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US